Re: [PATCH] [3/11] SYSCTL: Add proc_rcu_string to manage sysctlsusing rcu strings

[Paul E. McKenney]

On Mon, Dec 21, 2009 at 02:20:24AM +0100, Andi Kleen wrote:
> 
> Add a helper to use the new rcu strings for managing access
> to text sysctls. Conversions will be in follow-on patches.
> 
> An alternative would be to use seqlocks here, but RCU seemed
> cleaner.
> 
> Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>

Using the below as an example of my concern about access_rcu_string(), FYI.

> ---
>  include/linux/sysctl.h |    2 +
>  kernel/sysctl.c        |   66 +++++++++++++++++++++++++++++++++++++++++++++++++
>  kernel/sysctl_check.c  |    1 
>  3 files changed, 69 insertions(+)
> 
> Index: linux-2.6.33-rc1-ak/include/linux/sysctl.h
> ===================================================================
> --- linux-2.6.33-rc1-ak.orig/include/linux/sysctl.h
> +++ linux-2.6.33-rc1-ak/include/linux/sysctl.h
> @@ -969,6 +969,8 @@ typedef int proc_handler (struct ctl_tab
> 
>  extern int proc_dostring(struct ctl_table *, int,
>  			 void __user *, size_t *, loff_t *);
> +extern int proc_rcu_string(struct ctl_table *, int,
> +			 void __user *, size_t *, loff_t *);
>  extern int proc_dointvec(struct ctl_table *, int,
>  			 void __user *, size_t *, loff_t *);
>  extern int proc_dointvec_minmax(struct ctl_table *, int,
> Index: linux-2.6.33-rc1-ak/kernel/sysctl.c
> ===================================================================
> --- linux-2.6.33-rc1-ak.orig/kernel/sysctl.c
> +++ linux-2.6.33-rc1-ak/kernel/sysctl.c
> @@ -50,6 +50,7 @@
>  #include <linux/ftrace.h>
>  #include <linux/slow-work.h>
>  #include <linux/perf_event.h>
> +#include <linux/rcustring.h>
> 
>  #include <asm/uaccess.h>
>  #include <asm/processor.h>
> @@ -2016,6 +2017,60 @@ static int _proc_do_string(void* data, i
>  }
> 
>  /**
> + * proc_rcu_string - sysctl string with rcu protection
> + * @table: the sysctl table
> + * @write: %TRUE if this is a write to the sysctl file
> + * @buffer: the user buffer
> + * @lenp: the size of the user buffer
> + * @ppos: file position
> + *
> + * Handle a string sysctl similar to proc_dostring.
> + * The main difference is that the data pointer in the table
> + * points to a pointer to a string. The string should be initially
> + * pointing to a statically allocated (as a C object, not on the heap)
> + * default. When it is replaced old uses will be protected by
> + * RCU. The reader should use rcu_read_lock()/unlock() or
> + * access_rcu_string().
> + */
> +int proc_rcu_string(struct ctl_table *table, int write,
> +		void __user *buffer, size_t *lenp, loff_t *ppos)
> +{
> +	int ret;
> +
> +	if (write) {
> +		/* protect writers against each other */
> +		static DEFINE_MUTEX(rcu_string_mutex);
> +		char *old;
> +		char *new;
> +
> +		new = alloc_rcu_string(table->maxlen, GFP_KERNEL);
> +		if (!new)
> +			return -ENOMEM;
> +		mutex_lock(&rcu_string_mutex);
> +		old = *(char **)(table->data);
> +		strcpy(new, old);
> +		ret = _proc_do_string(new, table->maxlen, write, buffer, lenp, ppos);
> +		rcu_assign_pointer(*(char **)(table->data), new);
> +		/*
> +		 * For the first initialization allow constant strings.
> +		 */
> +		if (!kernel_address((unsigned long)old))
> +			free_rcu_string(old);
> +		mutex_unlock(&rcu_string_mutex);
> +	} else {
> +		char *str;
> +
> +		str = access_rcu_string(*(char **)(table->data), table->maxlen,
> +					GFP_KERNEL);

So the above statement picks up table->data, then some other CPU comes
in and executes the "write" side of this "if" statement, we get
preempted before access_rcu_string() enters its RCU read-side critical
section, the grace period elapse, we resume, and ... ouch!

One trick would be to make access_rcu_string() be a macro that does
first access to its first argument in an RCU read-side critical section.
Alternatively, pass in the address of the pointer, rather than the
pointer itself.

Or explain to me how I am confused.

> +		if (!str)
> +			return -ENOMEM;
> +		ret = _proc_do_string(str, table->maxlen, write, buffer, lenp, ppos);
> +		kfree(str);
> +	}
> +	return ret;
> +}
> +
> +/**
>   * proc_dostring - read a string sysctl
>   * @table: the sysctl table
>   * @write: %TRUE if this is a write to the sysctl file
> @@ -2030,6 +2085,10 @@ static int _proc_do_string(void* data, i
>   * and a newline '\n' is added. It is truncated if the buffer is
>   * not large enough.
>   *
> + * WARNING: this should be only used for read only strings
> + * or when you have a wrapper with special locking. Otherwise
> + * use proc_rcu_string to avoid races with the consumer.
> + *
>   * Returns 0 on success.
>   */
>  int proc_dostring(struct ctl_table *table, int write,
> @@ -2614,6 +2673,12 @@ int proc_dostring(struct ctl_table *tabl
>  	return -ENOSYS;
>  }
> 
> +int proc_rcu_string(struct ctl_table *table, int write,
> +		  void __user *buffer, size_t *lenp, loff_t *ppos)
> +{
> +	return -ENOSYS;
> +}
> +
>  int proc_dointvec(struct ctl_table *table, int write,
>  		  void __user *buffer, size_t *lenp, loff_t *ppos)
>  {
> @@ -2670,6 +2735,7 @@ EXPORT_SYMBOL(proc_dointvec_minmax);
>  EXPORT_SYMBOL(proc_dointvec_userhz_jiffies);
>  EXPORT_SYMBOL(proc_dointvec_ms_jiffies);
>  EXPORT_SYMBOL(proc_dostring);
> +EXPORT_SYMBOL(proc_rcu_string);
>  EXPORT_SYMBOL(proc_doulongvec_minmax);
>  EXPORT_SYMBOL(proc_doulongvec_ms_jiffies_minmax);
>  EXPORT_SYMBOL(register_sysctl_table);
> Index: linux-2.6.33-rc1-ak/kernel/sysctl_check.c
> ===================================================================
> --- linux-2.6.33-rc1-ak.orig/kernel/sysctl_check.c
> +++ linux-2.6.33-rc1-ak/kernel/sysctl_check.c
> @@ -131,6 +131,7 @@ int sysctl_check_table(struct nsproxy *n
>  				set_fail(&fail, table, "Directory with extra2");
>  		} else {
>  			if ((table->proc_handler == proc_dostring) ||
> +			    (table->proc_handler == proc_rcu_string) ||
>  			    (table->proc_handler == proc_dointvec) ||
>  			    (table->proc_handler == proc_dointvec_minmax) ||
>  			    (table->proc_handler == proc_dointvec_jiffies) ||
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/